© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 10942
    Prev
    Next
    INDEX
    Explanations

    XML or markup language elements with specific attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.71
     muco
    -0.51
    ↵↵↵
    -0.48
     dAtA
    -0.47
    <bos>
    -0.47
     forstå
    -0.46
    ců
    -0.44
     गति
    -0.43
    Gweler
    -0.43
    inerja
    -0.43
    POSITIVE LOGITS
    ագրություններ
    0.84
    rungsseite
    0.80
    awtextra
    0.76
     autorytatywna
    0.76
     snippetHide
    0.74
     kasarigan
    0.74
     الحره
    0.71
    Hozzáférés
    0.70
     مشين
    0.70
    Билгалдахарш
    0.70
    Activations Density 0.102%

    No Known Activations